INDEX

Explanations

phrases related to cruelty or inhuman treatment

oai_token-act-pair · gpt-3.5-turbo

terms related to cruelty and inhumane treatment

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aeda

-0.79

ucket

-0.78

kj

-0.76

 Bundle

-0.75

igating

-0.72

ernels

-0.71

ailed

-0.69

icans

-0.69

igate

-0.69

 Banking

-0.68

POSITIVE LOGITS

 cruelty

0.83

 cruel

0.80

 Cruel

0.75

ificial

0.70

est

0.70

 inhuman

0.69

 irony

0.69

 confinement

0.68

®

0.67

blooded

0.66

Activations Density 0.018%

phrases related to cruelty or inhuman treatment

terms related to cruelty and inhumane treatment

No Comments

No Known Activations